Prompt Caching 절감액 계산기
기본 모델을 선택하고 캐시 적중률, 쓰기 추가 요금 상각 및 월 청구액 감소 곡선을 정밀 시뮬레이션하세요.
OpenAI: GPT-6.1 Sol Prompt Caching
GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy professional...
GPT-4o (Omni) Prompt Caching
Flagship multimodal model for complex multimodal reasoning. 50% discount on cached prompt inputs (>1,024 tokens) and 50% discount on Batch API.
Claude 3.5 Sonnet Prompt Caching
Industry-leading coding and agentic performance. Prompt caching hits receive a 90% discount ($0.30/1M); initial cache writes incur 1.25x ($3.75/1M). Message Batches API grants 50% discount.
DeepSeek-V3 (deepseek-chat) Prompt Caching
General-purpose MoE model (671B total, 37B active). Automatic server-side context caching offers ~74.1% savings on cached hits. No async batch endpoint, but offers off-peak nighttime discounts (00:30-08:30 UTC+8) of 50%.
DeepSeek-R1 (deepseek-reasoner) Prompt Caching
Open-weights reasoning model with emergent reasoning capabilities. Reasoning tokens output rate is $2.19/1M. Automatic prefix caching yields ~74.5% input discount.
OpenAI: GPT-6.1 Terra Prompt Caching
GPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is particularly strong at understanding screen...
Anthropic: Claude Sonnet 5.5 Prompt Caching
Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and pro...
GPT-4o mini Prompt Caching
Cost-efficient lightweight flagship model replacing GPT-3.5 Turbo. Automatic 50% cache discount and 50% batch discount.
Gemini 1.5 Pro Prompt Caching
Massive 2M token context window for complex multimodal reasoning. Standard tier (<=128k prompt tokens): $1.25 input / $5.00 output; cached input discount is 75% ($0.3125/1M, with $4.50/1M/hr storage fee). Batch API provides 50% discount.
Gemini 1.5 Flash Prompt Caching
High-speed high-throughput model with 1M context window. Standard tier (<=128k prompt tokens): $0.075 input / $0.30 output; cached input discount is 75% ($0.01875/1M, with $1.00/1M/hr storage fee). Batch API provides 50% discount.
DeepSeek: DeepSeek V4.1 Flash Prompt Caching
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B o...
OpenAI o1 Prompt Caching
High-depth reasoning model using chain-of-thought tokens (billed as output tokens). Supports 200k context window and 100k completion tokens.
OpenAI o3-mini Prompt Caching
High-speed reasoning model specialized for STEM, mathematics, and complex coding at competitive pricing.
Llama 3.3 70B Versatile Prompt Caching
Powered by Groq LPUs delivering ultra-high token throughput (>300 tokens/sec). Prompt caching and batch processing provide 50% discount tiers.
SpaceXAI: Grok 4.5 Prompt Caching
Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.
Claude 3.5 Haiku Prompt Caching
High-velocity low-latency model. Prompt caching hit receives 90% discount ($0.08/1M); cache write at $1.00/1M. Message Batches API offers 50% off.
Mixtral 8x7B (32768) Prompt Caching
Sparse MoE architecture hosted on Groq LPU with extremely low latency. Symmetric $0.24/1M pricing. Legacy endpoint transitioning to Llama 3.x series.
Anthropic: Claude Opus 5 Prompt Caching
Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visu...
Anthropic: Claude Opus 5.5 Prompt Caching
Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large code...
Anthropic: Claude Sonnet 5 Prompt Caching
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort level...
DeepSeek: DeepSeek V4 Flash 0423 Prompt Caching
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for...
DeepSeek: DeepSeek V4 Flash 0731 Prompt Caching
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent wor...
DeepSeek: DeepSeek V4 Flash Vision Exp Prompt Caching
DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding image understanding w...
DeepSeek: DeepSeek V4 Pro 0423 Prompt Caching
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced re...
DeepSeek: DeepSeek V4 Pro 0813 Prompt Caching
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.
DeepSeek: DeepSeek V4.1 Flash 1017 Prompt Caching
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...
Google: Gemini 4 Argon Prompt Caching
Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to...
Google: Gemini 4 Carbon Prompt Caching
Gemini 4 Carbon is a frontier Gemini 4 model from Google for coding, agentic and complex reasoning work. It takes text, image, audio, video and file input, supports long decode...
Google: Gemini 4 Hydrogen Prompt Caching
Gemini 4 Hydrogen is the high-efficiency workhorse model of the Gemini 4 family from Google, built for high-throughput agentic workflows, coding and multi-model routing at lower cost and latency th...
OpenAI: GPT-5.6 Sol Prompt Caching
GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and multi-step coding tas...
OpenAI: GPT-5.6 Sol Pro Prompt Caching
GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **C...
OpenAI: GPT-5.6 Terra Prompt Caching
GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning, and agentic...
OpenAI: GPT-5.6 Terra Pro Prompt Caching
GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex task...
OpenAI: GPT-6 Astra Prompt Caching
GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creation, with particula...
OpenAI: GPT-6 Astra Pro Prompt Caching
GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **C...
OpenAI: GPT-6 Luna Prompt Caching
GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classification, and lig...